Quentin Gallouédec
commited on
Commit
•
afaac09
1
Parent(s):
ba0c3de
Initial commit
Browse files- .gitattributes +1 -0
- README.md +70 -0
- args.yml +83 -0
- config.yml +9 -0
- env_kwargs.yml +1 -0
- replay.mp4 +3 -0
- results.json +1 -0
- tqc-Swimmer-v3.zip +3 -0
- tqc-Swimmer-v3/_stable_baselines3_version +1 -0
- tqc-Swimmer-v3/actor.optimizer.pth +3 -0
- tqc-Swimmer-v3/critic.optimizer.pth +3 -0
- tqc-Swimmer-v3/data +115 -0
- tqc-Swimmer-v3/ent_coef_optimizer.pth +3 -0
- tqc-Swimmer-v3/policy.pth +3 -0
- tqc-Swimmer-v3/pytorch_variables.pth +3 -0
- tqc-Swimmer-v3/system_info.txt +7 -0
- train_eval_metrics.zip +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- Swimmer-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TQC
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: Swimmer-v3
|
16 |
+
type: Swimmer-v3
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 319.81 +/- 2.40
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **TQC** Agent playing **Swimmer-v3**
|
25 |
+
This is a trained model of a **TQC** agent playing **Swimmer-v3**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
|
27 |
+
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
|
28 |
+
|
29 |
+
The RL Zoo is a training framework for Stable Baselines3
|
30 |
+
reinforcement learning agents,
|
31 |
+
with hyperparameter optimization and pre-trained agents included.
|
32 |
+
|
33 |
+
## Usage (with SB3 RL Zoo)
|
34 |
+
|
35 |
+
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
|
36 |
+
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
|
37 |
+
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
|
38 |
+
|
39 |
+
Install the RL Zoo (with SB3 and SB3-Contrib):
|
40 |
+
```bash
|
41 |
+
pip install rl_zoo3
|
42 |
+
```
|
43 |
+
|
44 |
+
```
|
45 |
+
# Download model and save it into the logs/ folder
|
46 |
+
python -m rl_zoo3.load_from_hub --algo tqc --env Swimmer-v3 -orga qgallouedec -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo tqc --env Swimmer-v3 -f logs/
|
48 |
+
```
|
49 |
+
|
50 |
+
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
|
51 |
+
```
|
52 |
+
python -m rl_zoo3.load_from_hub --algo tqc --env Swimmer-v3 -orga qgallouedec -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo tqc --env Swimmer-v3 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo tqc --env Swimmer-v3 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo tqc --env Swimmer-v3 -f logs/ -orga qgallouedec
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('gamma', 0.9999),
|
66 |
+
('learning_starts', 10000),
|
67 |
+
('n_timesteps', 1000000.0),
|
68 |
+
('policy', 'MlpPolicy'),
|
69 |
+
('normalize', False)])
|
70 |
+
```
|
args.yml
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - algo
|
3 |
+
- tqc
|
4 |
+
- - conf_file
|
5 |
+
- null
|
6 |
+
- - device
|
7 |
+
- auto
|
8 |
+
- - env
|
9 |
+
- Swimmer-v3
|
10 |
+
- - env_kwargs
|
11 |
+
- null
|
12 |
+
- - eval_episodes
|
13 |
+
- 20
|
14 |
+
- - eval_freq
|
15 |
+
- 25000
|
16 |
+
- - gym_packages
|
17 |
+
- []
|
18 |
+
- - hyperparams
|
19 |
+
- null
|
20 |
+
- - log_folder
|
21 |
+
- logs
|
22 |
+
- - log_interval
|
23 |
+
- -1
|
24 |
+
- - max_total_trials
|
25 |
+
- null
|
26 |
+
- - n_eval_envs
|
27 |
+
- 5
|
28 |
+
- - n_evaluations
|
29 |
+
- null
|
30 |
+
- - n_jobs
|
31 |
+
- 1
|
32 |
+
- - n_startup_trials
|
33 |
+
- 10
|
34 |
+
- - n_timesteps
|
35 |
+
- -1
|
36 |
+
- - n_trials
|
37 |
+
- 500
|
38 |
+
- - no_optim_plots
|
39 |
+
- false
|
40 |
+
- - num_threads
|
41 |
+
- -1
|
42 |
+
- - optimization_log_path
|
43 |
+
- null
|
44 |
+
- - optimize_hyperparameters
|
45 |
+
- false
|
46 |
+
- - progress
|
47 |
+
- false
|
48 |
+
- - pruner
|
49 |
+
- median
|
50 |
+
- - sampler
|
51 |
+
- tpe
|
52 |
+
- - save_freq
|
53 |
+
- -1
|
54 |
+
- - save_replay_buffer
|
55 |
+
- false
|
56 |
+
- - seed
|
57 |
+
- 3962785800
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- runs/Swimmer-v3__tqc__3962785800__1676710082
|
64 |
+
- - track
|
65 |
+
- true
|
66 |
+
- - trained_agent
|
67 |
+
- ''
|
68 |
+
- - truncate_last_trajectory
|
69 |
+
- true
|
70 |
+
- - uuid
|
71 |
+
- false
|
72 |
+
- - vec_env
|
73 |
+
- dummy
|
74 |
+
- - verbose
|
75 |
+
- 1
|
76 |
+
- - wandb_entity
|
77 |
+
- openrlbenchmark
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
82 |
+
- - yaml_file
|
83 |
+
- null
|
config.yml
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - gamma
|
3 |
+
- 0.9999
|
4 |
+
- - learning_starts
|
5 |
+
- 10000
|
6 |
+
- - n_timesteps
|
7 |
+
- 1000000.0
|
8 |
+
- - policy
|
9 |
+
- MlpPolicy
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
replay.mp4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c6fa17e01f55d42809b52c258afce632f210844ac48e3901dc628473dbb6b23
|
3 |
+
size 1303985
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 319.8090664, "std_reward": 2.40137736697631, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T18:04:32.355996"}
|
tqc-Swimmer-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e3f499656a3b76dd94cd280760d7135f1f032b7b26c600a9adc9efdb3dd4dcb
|
3 |
+
size 3279816
|
tqc-Swimmer-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0a6
|
tqc-Swimmer-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc5810570cd1b81eb0928ae96623127dca59d44f3657b4b7922dcb6a3ccaa77
|
3 |
+
size 559517
|
tqc-Swimmer-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52bb4be65e79092e478c71f793f8bdd67b83a816c7c09342d304ca281e818020
|
3 |
+
size 1210105
|
tqc-Swimmer-v3/data
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVKgAAAAAAAACMGHNiM19jb250cmliLnRxYy5wb2xpY2llc5SMCVRRQ1BvbGljeZSTlC4=",
|
5 |
+
"__module__": "sb3_contrib.tqc.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TQC.\n\n :param observation_space: Observation space\n :param action_space: Action space\n :param lr_schedule: Learning rate schedule (could be constant)\n :param net_arch: The specification of the policy and value networks.\n :param activation_fn: Activation function\n :param use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE to ensure\n a positive standard deviation (cf paper). It allows to keep variance\n above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n :param clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the feature extractor.\n :param normalize_images: Whether to normalize images or not,\n dividing by 255.0 (True by default)\n :param optimizer_class: The optimizer to use,\n ``th.optim.Adam`` by default\n :param optimizer_kwargs: Additional keyword arguments,\n excluding the learning rate, to pass to the optimizer\n :param n_quantiles: Number of quantiles for the critic.\n :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
7 |
+
"__init__": "<function TQCPolicy.__init__ at 0x7ff9203a6670>",
|
8 |
+
"_build": "<function TQCPolicy._build at 0x7ff9203a6700>",
|
9 |
+
"_get_constructor_parameters": "<function TQCPolicy._get_constructor_parameters at 0x7ff9203a6790>",
|
10 |
+
"reset_noise": "<function TQCPolicy.reset_noise at 0x7ff9203a6820>",
|
11 |
+
"make_actor": "<function TQCPolicy.make_actor at 0x7ff9203a68b0>",
|
12 |
+
"make_critic": "<function TQCPolicy.make_critic at 0x7ff9203a6940>",
|
13 |
+
"forward": "<function TQCPolicy.forward at 0x7ff9203a69d0>",
|
14 |
+
"_predict": "<function TQCPolicy._predict at 0x7ff9203a6a60>",
|
15 |
+
"set_training_mode": "<function TQCPolicy.set_training_mode at 0x7ff9203a6af0>",
|
16 |
+
"__abstractmethods__": "frozenset()",
|
17 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff9203a90c0>"
|
18 |
+
},
|
19 |
+
"verbose": 1,
|
20 |
+
"policy_kwargs": {
|
21 |
+
"use_sde": false
|
22 |
+
},
|
23 |
+
"observation_space": {
|
24 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"dtype": "float64",
|
27 |
+
"_shape": [
|
28 |
+
8
|
29 |
+
],
|
30 |
+
"low": "[-inf -inf -inf -inf -inf -inf -inf -inf]",
|
31 |
+
"high": "[inf inf inf inf inf inf inf inf]",
|
32 |
+
"bounded_below": "[False False False False False False False False]",
|
33 |
+
"bounded_above": "[False False False False False False False False]",
|
34 |
+
"_np_random": null
|
35 |
+
},
|
36 |
+
"action_space": {
|
37 |
+
":type:": "<class 'gym.spaces.box.Box'>",
|
38 |
+
":serialized:": "gAWVDgwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAIC/AACAv5RoCksChZSMAUOUdJRSlIwEaGlnaJRoEiiWCAAAAAAAAAAAAIA/AACAP5RoCksChZRoFXSUUpSMDWJvdW5kZWRfYmVsb3eUaBIolgIAAAAAAAAAAQGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAoWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYCAAAAAAAAAAEBlGghSwKFlGgVdJRSlIwKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwSX19yYW5kb21zdGF0ZV9jdG9ylJOUjAdNVDE5OTM3lGgtjBRfX2JpdF9nZW5lcmF0b3JfY3RvcpSTlIaUUpR9lCiMDWJpdF9nZW5lcmF0b3KUjAdNVDE5OTM3lIwFc3RhdGWUfZQojANrZXmUaBIolsAJAAAAAAAAAAAAgFPCs5yHA7WTcuyrW+jmsvLPtoHa1QbvYaExTaBrtczZE+YYn3SceS/IpRuAxHkBSZ4PQ+Rd4BiTkhNVzNRKKWTSCJW+NNCeRHJ6A/Ctvwpzm3s+6WCxBtp1A0ULbn3WFmrrBDRmg7fz9aUvae9CY0O1XPfCd1LMRkQ3LQiJbtCOrnf7GLaAT3ue+U8y7BLYuY5ehakZyq49di1nK0KAnsXuxx/1IgFdS88kD8wZUmREV5hwnQr1Ehe16VreO8T/Qc86sV+2h90z2FiJqqLNf3s/yZS3bA9DHzGZfRtgkKu3Bx0ZTN7I+466APXPqRreJf4gBqUW/NB248FO9cpD0wFaed9QV63NqpiFOs/RYeEwD8e32dZFRfi9SK5aLvuApJMu2LOfZweypHIkyPjeY5W+tsm2bdPmVoCAOiyi73cf5k0LQeJNWqZU/wuy/f8myghZ9qrjf+2JSJMaB9VNMXWmxuq4Dq0fkhzJr1ML7SgftfSG29O5koFUMozQL58gAzyX96ZMcpWbZ+3/zlaVhGln5egXC8MtIK6xIFCvh/vD/F1jLgYIp14MM597MuPmTpa+OaKek7bql9Cp8/0skhg5QSCvCaijm8wenxrfqLyRxDPCpS+L3isJC5LrjFgWnsdxQXVrJK8uaobJcTIJ5NrYYfA2l5gH27iPI9EqhzFtZJXiE4vXpH18f3kouYV9RowPzOtmYsbmstR/Mx/VY7E0XBmnMidL4dYTUXgxaDbFxWy3y6miL2yw0I2O09vPWV7LqbwMbthlU26lrLfnJDz88B+7y4pFCwvsHgCsMWq6pvroAF4Ms+++JnhzrL0GLrtfJ7667p42Vg78GirmKIRMFH0p6aLRPV4V/fclE3PLBj0InU315M5v7fDFj/IreJeFUhIAy5/BlvLdgwIfBMBWvyjhqGRBo2KmdiDAO9BPhdi6oGmZUCxTDjUyMd8rjeRdntTE+L9sHQUSvUfpRjKcSIjZXcjsMMSwwU0QzIXewD4nZg8EAZ72iHnChWveW7cB5EQRFE+YPvvyNAw4OvORF+DjDtmLUz6jNz0JbkuKbhIQEEVbpDRkoeIGA4HATymZeE4TX/hvhOxJfX5liXD9/Uon8OjJ/hhIrDNUYR2NOV2R1L+VuK/JA9o0izGPiCC9vi7UK1u4re8tvPrBInC6BH2DpMvWSRepdH0frFxGsH/kRB/S77USeMs38a+yorDaa9Wsb9WnuQg10vl087jhvwSZx77fGq52NV1h/UnZAjnqJOjCPBgQrY0wsSeSW6SOSdItAOupiWkVvSzHz+gopd/3FUUPbjdik7Vd6O6ycGOFwp4+wyZqq1MKHww5exJND6De8NB4fGBzsvKoT8O1fAC3Y2Z+3mLYwkCJXULx2zNSO90bQi0L0BhTF1AidNtqRkak72V+V1kos6m4F+kyZiOiwxfcHKWHmpQe3A8HpX6nacx0Zso0WyF/W/sOLo//2g0YD9koIjgKvw//f9Em4CvxNBUMnJYTVQJGysF4QMShnM6byaMNJhRVALf+X0+SgLJkEwLfKdBbKxjA035OEc2YKmUpvooVUUt+9U8d7cKRgNYKKPwCHyYfLJSQt4ZEdThgjeywDxgsGzPax5SklOLroSYn39feofatZDzJXevfPTHyi1ZLwpe6Hwkbqz1FuOnHiShPedbEA9b/HCtBytSZrgUwlwHpQlAiBTSxpN7TFzVZrrhRd6N8W+FeE9SAGCHwXchFR4SCGThPyRGO/XWkMPJ42BLUOmMGepDQgWH646tjoJSE3EXcA5iDS+Nq6Oh521oC2UPAnvxIj1QbVh8IbxlBytRTTjc0c14E9cyhIPlgIoHriuEFSMXSEzOGL1MmL6UCbiXfsRg9Z6OwWCCl3VeGg5bEZ1kjJkvs08k7wtPk4ATAjaTL3QoY2gf106zFbJtL4D5gmLMJ9OuzE2Fn5uaAqqpjXIqqEXxS9jtpsRU9VTHCg68RwXQVIUhuVJgHq8fOigBMrW7Am5+jjo/GNNlcFcp813dFiXy4qHhjGSEjNXp3ln03NZkOgqXQ8SalJlPOvyrAS9wW9EtjQKhcrBSWSsQ8C3o/Mc/sR/CMRB85ZIojR/tiCKtOutxQMIusIOnYHK8g6kPpTQ8J/PfJ8pa3GEoYoA67axQTXsysd2Y6ZDwpz1HkAeISVK2AlCcuQssrQv8dVLAcins/2kjRFp5Vp82HSX9j6Ci9GH5mkdyqV84vWsdwRz4JNXHZoHVZKnrxSdA1HUwRUI/5oWiqnGk9KyiS4Mv9dQIVluJ1+/pAHYEdG9YgLHiNE2zA7aIQbqqlGX6jH1CrHSPL9mnlHdPiKjozwRXu02UQuzlGJn+/PUkU6cPYLLeLc8e7S2qfCZxbdpHioand7wYKqb5bMb8dA3Dwvm6P6iJXSogJ+Q+0z43li8ydYJqZNZlSjsljr/2c5UU33vMhLDLEXIHT8WzrsS45TsKNbhYfTYx6Ds/8W5yOtiOPWc0+fRlAjbQC++FKo5UaMl2eRCxI4U5/heX2HxJGNk50rICjuFsG/8Q+NUuJgS+y3FMhe+sm1e2MdC+ldkBqEn8oRxajECbP4Wizz1tfJliW/1A5fdGTfUxM3HV72bJgnqswmoAumAx6d36KfuZwEEp0/wcrdo+8/unJ5f2mYeqCrOcaxDJrs6SxW1zVaH/YTZl+RNA0NjPLgaqnlveaes/MkpzsVEQDtvKGFrG1cnmGjZVi2azrSDGQ0Y423nEksDC5awYcOJmVYbeA4DkMSNfj+7Dx2SzH/PVPuXLX9aw9K9QF4Ml48zsSrwsVjIa8+gIdffs2pf2wCKcPtFez6vOT0UDuFHknJjMDg0fI3DnyC7jJqO8V4XpmPyarTp3JJRGhmqTHhpZInn70JMfS+RFry5+rLSOM0T+KWV8fYjs9eyCiZijlR4AiADooXm9G8JIzZCLZX2Dty83iyz7gQzSxYO7ULuTT1stvGuJwbBP4LMhLXkbxdhAmBSDiYNOnc3O+yFsO6Ps9UOQD8S4Pbr8hZ4mFjbicpO635SwpmHINYDeuewln3/GHz69LpCjmpnKPeF9ZxXcq6MR4kJUV2j/dQzqjLniNaQmrMkULdI7W1sMXRFcsz9xs1GVwVqmtMVws8HtvXMYNmosCrrgAFX2ghPz7dXCV6vML5YhfNbDAzzG6MHffrslrhMav3vtlt8Fnld4VaH6IhMkowayT1lSVvfvlKHCWwtKaTcOZrR5LZGalJOpFbVIFUOAo+LnY/25bmc3KloyLzgiTudjPsXEGPNPBIvE/5cMEvU4Lrs0N3tCke4abYDXF9f14QrwLlGgHjAJ1NJSJiIeUUpQoSwNoC05OTkr/////Sv////9LAHSUYk1wAoWUaBV0lFKUjANwb3OUTXACdYwJaGFzX2dhdXNzlEsAjAVnYXVzc5RHAAAAAAAAAAB1YnViLg==",
|
39 |
+
"dtype": "float32",
|
40 |
+
"_shape": [
|
41 |
+
2
|
42 |
+
],
|
43 |
+
"low": "[-1. -1.]",
|
44 |
+
"high": "[1. 1.]",
|
45 |
+
"bounded_below": "[ True True]",
|
46 |
+
"bounded_above": "[ True True]",
|
47 |
+
"_np_random": "RandomState(MT19937)"
|
48 |
+
},
|
49 |
+
"n_envs": 1,
|
50 |
+
"num_timesteps": 1000000,
|
51 |
+
"_total_timesteps": 1000000,
|
52 |
+
"_num_timesteps_at_start": 0,
|
53 |
+
"seed": 0,
|
54 |
+
"action_noise": null,
|
55 |
+
"start_time": 1676710084880565805,
|
56 |
+
"learning_rate": 0.0003,
|
57 |
+
"tensorboard_log": "runs/Swimmer-v3__tqc__3962785800__1676710082/Swimmer-v3",
|
58 |
+
"lr_schedule": {
|
59 |
+
":type:": "<class 'function'>",
|
60 |
+
":serialized:": "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"
|
61 |
+
},
|
62 |
+
"_last_obs": null,
|
63 |
+
"_last_episode_starts": {
|
64 |
+
":type:": "<class 'numpy.ndarray'>",
|
65 |
+
":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
|
66 |
+
},
|
67 |
+
"_last_original_obs": {
|
68 |
+
":type:": "<class 'numpy.ndarray'>",
|
69 |
+
":serialized:": "gAWVtQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJZAAAAAAAAAAOx7Klbsp+m/LbYKYEck8T81IONgTRnfPzTlgaG78s0/EXRC9zek47+2YubEF0G0P3X/vTX2Pv+/bUJMzhraEUCUjAVudW1weZSMBWR0eXBllJOUjAJmOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLCIaUjAFDlHSUUpQu"
|
70 |
+
},
|
71 |
+
"_episode_num": 1000,
|
72 |
+
"use_sde": false,
|
73 |
+
"sde_sample_freq": -1,
|
74 |
+
"_current_progress_remaining": 0.0,
|
75 |
+
"ep_info_buffer": {
|
76 |
+
":type:": "<class 'collections.deque'>",
|
77 |
+
":serialized:": "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"
|
78 |
+
},
|
79 |
+
"ep_success_buffer": {
|
80 |
+
":type:": "<class 'collections.deque'>",
|
81 |
+
":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
|
82 |
+
},
|
83 |
+
"_n_updates": 990000,
|
84 |
+
"buffer_size": 1,
|
85 |
+
"batch_size": 256,
|
86 |
+
"learning_starts": 10000,
|
87 |
+
"tau": 0.005,
|
88 |
+
"gamma": 0.9999,
|
89 |
+
"gradient_steps": 1,
|
90 |
+
"optimize_memory_usage": false,
|
91 |
+
"replay_buffer_class": {
|
92 |
+
":type:": "<class 'abc.ABCMeta'>",
|
93 |
+
":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
|
94 |
+
"__module__": "stable_baselines3.common.buffers",
|
95 |
+
"__doc__": "\n Replay buffer used in off-policy algorithms like SAC/TD3.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n of the replay buffer which reduces by almost a factor two the memory used,\n at a cost of more complexity.\n See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n Cannot be used in combination with handle_timeout_termination.\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
96 |
+
"__init__": "<function ReplayBuffer.__init__ at 0x7ff92082e5e0>",
|
97 |
+
"add": "<function ReplayBuffer.add at 0x7ff92082e670>",
|
98 |
+
"sample": "<function ReplayBuffer.sample at 0x7ff92082e700>",
|
99 |
+
"_get_samples": "<function ReplayBuffer._get_samples at 0x7ff92082e790>",
|
100 |
+
"__abstractmethods__": "frozenset()",
|
101 |
+
"_abc_impl": "<_abc._abc_data object at 0x7ff920829300>"
|
102 |
+
},
|
103 |
+
"replay_buffer_kwargs": {},
|
104 |
+
"train_freq": {
|
105 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
106 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
107 |
+
},
|
108 |
+
"use_sde_at_warmup": false,
|
109 |
+
"target_entropy": -2.0,
|
110 |
+
"ent_coef": "auto",
|
111 |
+
"target_update_interval": 1,
|
112 |
+
"top_quantiles_to_drop_per_net": 2,
|
113 |
+
"batch_norm_stats": [],
|
114 |
+
"batch_norm_stats_target": []
|
115 |
+
}
|
tqc-Swimmer-v3/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19fb25adf65b03f4f4453d38ee2238ee581ee231c207abcb8138099100e366fa
|
3 |
+
size 1507
|
tqc-Swimmer-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad851cb8d56da342861b5212e6c32089c065860668b67eaa6981e03d235ed08d
|
3 |
+
size 1487877
|
tqc-Swimmer-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6946c9971e5ef03732970f009c2a637273b3a04e1ff34b95ccd77ba9f1f8242f
|
3 |
+
size 747
|
tqc-Swimmer-v3/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
|
2 |
+
- Python: 3.9.12
|
3 |
+
- Stable-Baselines3: 1.8.0a6
|
4 |
+
- PyTorch: 1.13.1+cu117
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.24.1
|
7 |
+
- Gym: 0.21.0
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e08e945c961a394f5f2ca0dabbefdacce6171df5dfbc47dbfaab534f8ca16af
|
3 |
+
size 42356
|